© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144199
    Prev
    Next
    INDEX
    Explanations

    ligation, Suisse,//@version, dog, inFP, initial idea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    人
    1.41
    1.38
    是用
    1.23
    ని
    1.20
    的
    1.20
    ität
    1.19
    }.
    1.16
    ský
    1.14
    其他
    1.13
    ன்
    1.10
    POSITIVE LOGITS
    י
    1.91
    бо
    1.49
    arı
    1.48
    ে
    1.48
    ’
    1.48
    те
    1.44
    ру
    1.38
    мі
    1.38
    в
    1.38
    ס
    1.38
    Activations Density 0.000%

    No Known Activations